20‑Year‑Old Transformer Co‑author Open‑Sources a 218‑Billion‑Parameter Model

Cohere’s Command A+ model, built by Transformer co‑author Aidan Gomez and backed by Nick Frosst, packs 218 billion parameters but activates only 25 billion at inference, uses a lossless 4‑bit quantization scheme, offers native citation support, runs on a single B200 or two H100 GPUs, and is released under an Apache 2.0 license, marking a major shift toward truly open‑source, enterprise‑ready large language models.

AIApache-2.0Cohere

0 likes · 12 min read

20‑Year‑Old Transformer Co‑author Open‑Sources a 218‑Billion‑Parameter Model

James' Growth Diary

May 20, 2026 · Artificial Intelligence

Boosting RAG Retrieval Quality with Cohere Rerank and Cross‑Encoder

After achieving high recall with hybrid Elasticsearch and vector search, the article shows how inserting a reranker—either Cohere's cloud API or a local Cross‑Encoder—compresses the top‑20 candidates to the most relevant three to five, dramatically improving answer accuracy, cutting token costs, and detailing a dual‑track implementation for production and development environments.

CohereCross-EncoderLangChain

0 likes · 22 min read

Boosting RAG Retrieval Quality with Cohere Rerank and Cross‑Encoder

AI Large Model Application Practice

Nov 8, 2024 · Artificial Intelligence

How to Build a Multimodal Embedding RAG with Cohere and LlamaIndex

This guide explains how to overcome the limitations of text‑only embeddings for enterprise AI search by using a multimodal embedding model to index and retrieve both text and images, detailing the full workflow, code examples, and performance benefits.

CohereLLMLlamaIndex

0 likes · 13 min read

How to Build a Multimodal Embedding RAG with Cohere and LlamaIndex

AI Large Model Application Practice

Jun 17, 2024 · Artificial Intelligence

Boost Your RAG Pipeline with Cohere and BGE Rerank Models

This guide explains why post‑retrieval reranking is essential for Retrieval‑Augmented Generation, compares the commercial Cohere Rerank service with the open‑source bge‑reranker‑large model, and provides step‑by‑step code for integrating both into LlamaIndex pipelines, including a custom TEI‑based processor.

BGECohereLlamaIndex

0 likes · 11 min read

Boost Your RAG Pipeline with Cohere and BGE Rerank Models